ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges
Not on the map. Why?
Abstract (arXiv)
The fifth Affective Behavior Analysis in-the-wild (ABAW) Competition is part of the respective ABAW Workshop which will be held in conjunction with IEEE Computer Vision and Pattern Recognition Conference (CVPR), 2023. The 5th ABAW Competition is a continuation of the Competitions held at ECCV 2022, IEEE CVPR 2022, ICCV 2021, IEEE FG 2020 and CVPR 2017 Conferences, and is dedicated at automatically analyzing affect. For this year's Competition, we feature two corpora: i) an extended version of the Aff-Wild2 database and ii) the Hume-Reaction dataset. The former database is an audiovisual one of around 600 videos of around 3M frames and is annotated with respect to:a) two continuous affect dimensions -valence (how positive/negative a person is) and arousal (how active/passive a person is)-; b) basic expressions (e.g. happiness, sadness, neutral state); and c) atomic facial muscle actions (i.e., action units). The latter dataset is an audiovisual one in which reactions of individuals to emotional stimuli have been annotated with respect to seven emotional expression intensities. Thus the 5th ABAW Competition encompasses four Challenges: i) uni-task Valence-Arousal Estimation, ii) uni-task Expression Classification, iii) uni-task Action Unit Detection, and iv) Emotional Reaction Intensity Estimation. In this paper, we present these Challenges, along with their corpora, we outline the evaluation metrics, we present the baseline systems and illustrate their obtained performance.
Key facts. Cited by 110 papers in the map (data through 7 Oct 2026). Builds on 70 of its 116 references that are in the map. First posted on arXiv 2 Mar 2023.
Builds on
70 of 116 references.
References · 70
- 2019Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFacecited by 222
- 2018Deep Affect Prediction in-the-wild: Aff-Wild Database and Challenge, Deep Architectures, and Beyondcited by 216
- 2020Analysing Affective Behavior in the First ABAW 2020 Competitioncited by 178
- 2021Affect Analysis in-the-wild: Valence-Arousal, Expressions, Action Units and a Unified Frameworkcited by 174
- 2021Distribution Matching for Heterogeneous Multi-Task Learning: a Large-scale Face Studycited by 168
- 2021Analysing Affective Behavior in the second ABAW2 Competitioncited by 163
- 2022ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Multi-Task Learning Challengescited by 156
- 2019Face Behavior a la carte: Expressions, Affect and Action Units in a Single Networkcited by 155
- 2022ABAW: Learning from Synthetic Data & Multi-Task Learning Challengescited by 110
- 2018Aff-Wild2: Extending the Aff-Wild Database for Affect Recognitioncited by 80
- 2020Deep Transparent Prediction through Latent Representation Analysiscited by 72
- 2021MIA-COV19D: COVID-19 Detection through 3-D Chest CT Image Analysiscited by 72
38 more
- 2020Two-Stream Aural-Visual Affect Analysis in the Wildcited by 51
- 2022Transformer-based Multimodal Information Fusion for Facial Expression Analysiscited by 49
- 2019Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Datasetcited by 39
- 2020Multitask Emotion Recognition with Incomplete Labelscited by 39
- 2018Photorealistic Facial Synthesis in the Dimensional Affect Spacecited by 33
- 2022A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognitioncited by 33
- 2022MixAugment & Mixup: Augmentation Methods for Facial Expression Recognitioncited by 31
- 2018A Multi-Task Learning & Generation Framework: Valence-Arousal, Action Units & Primary Expressionscited by 25
- 2021A Multi-modal and Multi-task Learning Method for Action Unit and Expression Recognitioncited by 24
- 2022The MuSe 2022 Multimodal Sentiment Analysis Challenge: Humor, Emotional Reactions, and Stresscited by 23
- 2018Training Deep Neural Networks with Different Datasets In-the-wild: The Emotion Recognition Paradigmcited by 20
- 2022Continuous Emotion Recognition using Visual-audio-linguistic information: A Technical Report for ABAW3cited by 20
- 2021A Multi-task Mean Teacher for Semi-supervised Facial Affective Behavior Analysiscited by 19
- 2021Prior Aided Streaming Network for Multi-task Affective Recognitionat the 2nd ABAW2 Competitioncited by 18
- 2022Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognitioncited by 17
- 2017Incremental Boosting Convolutional Neural Network for Facial Action Unit Recognitioncited by 16
- 2022Frame-level Prediction of Facial Expressions, Valence, Arousal and Action Units for Mobile Devicescited by 16
- 2023MMA-MRNNet: Harnessing Multiple Models of Affect and Dynamic Masked RNN for Precise Facial Expression Intensity Estimationcited by 16
- 2018A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wildcited by 15
- 2022Multi-modal Emotion Estimation for in-the-wild Videoscited by 15
- 2020M3T: Multi-Modal Continuous Valence-Arousal Estimation in the Wildcited by 14
- 2020Affect Expression Behaviour Analysis in the Wild using Spatio-Channel Attention and Complementary Context Informationcited by 13
- 2021An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wildcited by 12
- 2021Multitask Multi-database Emotion Recognitioncited by 12
- 2022Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysiscited by 12
- 2022Facial Action Unit Recognition With Multi-models Ensemblingcited by 10
- 2022Multi-modal Multi-label Facial Action Unit Detection with Transformercited by 10
- 2022Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challengescited by 10
- 2022Affective Behaviour Analysis Using Pretrained Model with Facial Prioricited by 10
- 2022Multi-label Transformer for Action Unit Detectioncited by 9
- 2022Multiple Emotion Descriptors Estimation at the ABAW3 Challengecited by 9
- 2022An Ensemble Approach for Facial Expression Analysis in Videocited by 9
- 2022Facial Expression Recognition with Swin Transformercited by 9
- 2020Emotion Recognition for In-the-wild Videoscited by 8
- 2020Affective Expression Analysis in-the-wild using Multi-Task Temporal Statistical Deep Learning Modelcited by 8
- 2020A Multi-term and Multi-task Analyzing Framework for Affective Analysis in-the-wildcited by 8
- 2020An Audio-Video Deep and Transfer Learning Framework for Multimodal Emotion Recognition in the wildcited by 8
- 2021Technical Report for Valence-Arousal Estimation on Affwild2 Datasetcited by 8
50 most cited of 70 All 70 (JSON)
Built on by
Citing papers per year: 2023: 26; 2024: 45; 2025: 22; 2026: 17.
110 papers.
Sort:
By area:
- 2024The 6th Affective Behavior Analysis in-the-wild (ABAW) Competitioncited by 78
- 2024Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyondcited by 60
- 20247th ABAW Competition: Multi-Task Learning and Compound Expression Recognitioncited by 53
- 2023From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videoscited by 39
- 2024Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scanscited by 30
- 2023Multi-modal Facial Affective Analysis based on Masked Autoencodercited by 23
- 2024COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI Systemcited by 23
- 2023Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognitioncited by 20
- 2023BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classificationcited by 20
- 2024Affective Behaviour Analysis via Integrating Multi-Modal Knowledgecited by 18
- 2024Robust Light-Weight Facial Affective Behavior Recognition with CLIPcited by 16
- 2024Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkitcited by 16
38 more
- 2024Recursive Joint Cross-Modal Attention for Multimodal Fusion in Dimensional Emotion Recognitioncited by 15
- 2025HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognitioncited by 15
- 2024MMA-DFER: MultiModal Adaptation of unimodal models for Dynamic Facial Expression Recognition in-the-wildcited by 14
- 2024SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detectioncited by 14
- 2024Joint Multimodal Transformer for Emotion Recognition in the Wildcited by 13
- 2025DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarioscited by 13
- 2023ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learningcited by 9
- 2024Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wildcited by 9
- 2023A transformer-based approach to video frame-level prediction in Affective Behaviour Analysis In-the-wildcited by 8
- 2023Multi-modal Facial Action Unit Detection with Large Pre-trained Models for the 5th Competition on Affective Behavior Analysis in-the-wildcited by 8
- 2024Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modelingcited by 8
- 2024Can Machine Learning Assist in Diagnosis of Primary Immune Thrombocytopenia? A feasibility studycited by 8
- 2024Affective Behavior Analysis using Task-adaptive and AU-assisted Graph Networkcited by 8
- 2024Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks: Application to 7th ABAW Challengecited by 8
- 2025MAVEN: Multi-modal Attention for Valence-Arousal Emotion Networkcited by 8
- 2023EmotiEffNet Facial Features in Uni-task Emotion Recognition in Video at ABAW-5 competitioncited by 7
- 2023Spatio-Temporal AU Relational Graph Representation Learning For Facial Action Units Detectioncited by 7
- 2024Affective Behaviour Analysis via Progressive Learningcited by 7
- 2024Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistencycited by 7
- 2023Facial Affective Behavior Analysis Method for 5th ABAW Competitioncited by 6
- 2023Facial Affect Recognition based on Transformer Encoder and Audiovisual Fusion for the ABAW5 Challengecited by 6
- 2024Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformerscited by 6
- 2024Efficient Feature Extraction and Late Fusion Strategy for Audiovisual Emotional Mimicry Intensity Estimationcited by 6
- 2024Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Predictioncited by 6
- 2024CAGE: Circumplex Affect Guided Expression Inferencecited by 6
- 2024HSEmotion Team at the 7th ABAW Challenge: Multi-Task Learning and Compound Facial Expression Recognitioncited by 6
- 2024Ig3D: Integrating 3D Face Representations in Facial Expression Inferencecited by 6
- 2024Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Stylecited by 6
- 2025Emotion Recognition with CLIP and Sequential Learningcited by 6
- 2025Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Spacecited by 6
- 2023Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detectioncited by 5
- 2023Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformerscited by 5
- 2023TempT: Temporal consistency for Test-time adaptationcited by 5
- 2024Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimationcited by 5
- 2025Semantic Matters: Multimodal Features for Affective Analysiscited by 5
- 2023Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognitioncited by 4
- 2023Vision Transformer for Action Units Detectioncited by 4
- 2024SUN Team's Contribution to ABAW 2024 Competition: Audio-visual Valence-Arousal Estimation and Expression Recognitioncited by 4
50 most cited of 110 All 110 (JSON)
- 2026AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis17 Jul 2026
- 2026AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow14 Jul 2026
- 2026HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognition14 Jul 2026
- 2026Causal Supervision of Attention for Affective Behaviour Analysis13 Jul 2026
- 2026Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition12 Jul 2026
- 2026A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition11 Jul 2026
- 2026The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognition14 Jun 2026
- 2026SenBen: Sensitive Scene Graphs for Explainable Content Moderation9 Apr 2026
- 2026Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation16 Mar 2026
- 2026Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach13 Mar 2026
- 2026HSEmotion Team at ABAW-10 Competition: Facial Expression Recognition, Valence-Arousal Estimation, Action Unit Detection and Fine-Grained Violence Classification13 Mar 2026
- 2026A Two-Stage Dual-Modality Model for Facial Emotional Expression Recognition12 Mar 2026
38 more
- 2026Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling12 Mar 2026
- 2026Stage-Adaptive Reliability Modeling for Continuous Valence-Arousal Estimation12 Mar 2026
- 2026Facial-Expression-Aware Prompting for Empathetic LLM Tutoring10 Mar 2026
- 2026Solution to the 10th ABAW Expression Recognition Challenge: A Robust Multimodal Framework with Safe Cross-Attention and Modality Dropout9 Mar 2026
- 2026Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions1 Jan 2026
- 2025Emotions as Ambiguity-aware Ordinal Representations26 Aug 2025
- 2025Grounding Emotion Recognition with Visual Prototypes: VEGA -- Revisiting CLIP in MERC6 Aug 2025
- 2025Multimodal Alignment with Cross-Attentive GRUs for Fine-Grained Video Understanding4 Jul 2025
- 2025Team RAS in 9th ABAW Competition: Multimodal Compound Expression Recognition Approach2 Jul 2025
- 2025DVD: A Comprehensive Dataset for Advancing Violence Detection in Real-World Scenarios29 May 2025
- 2025Multimodal Representation Learning Techniques for Comprehensive Facial State Analysis14 Apr 2025
- 2025FIESTA: Fisher Information-based Efficient Selective Test-time Adaptation29 Mar 2025
- 2025V-NAW: Video-based Noise-aware Adaptive Weighting for Facial Expression Recognition20 Mar 2025
- 2025Semantic Matters: Multimodal Features for Affective Analysis16 Mar 2025
- 2025MAVEN: Multi-modal Attention for Valence-Arousal Emotion Network16 Mar 2025
- 2025United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space15 Mar 2025
- 2025Enhancing Facial Expression Recognition through Dual-Direction Attention Mixed Feature Networks and CLIP: Application to 8th ABAW Challenge15 Mar 2025
- 2025Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusion15 Mar 2025
- 2025Compound Expression Recognition via Large Vision-Language Models14 Mar 2025
- 2025Solution for 8th Competition on Affective & Behavior Analysis in-the-wild14 Mar 2025
- 2025Technical Approach for the EMI Challenge in the 8th Affective Behavior Analysis in-the-Wild Competition13 Mar 2025
- 2025Lightweight Models for Emotional Analysis in Video13 Mar 2025
- 2025HSEmotion Team at ABAW-8 Competition: Audiovisual Ambivalence/Hesitancy, Emotional Mimicry Intensity and Facial Expression Recognition13 Mar 2025
- 2025Mamba-VA: A Mamba-based Approach for Continuous Emotion Recognition in Valence-Arousal Space13 Mar 2025
- 2025Emotion Recognition with CLIP and Sequential Learning13 Mar 2025
- 20257ABAW-Compound Expression Recognition via Curriculum Learning11 Mar 2025
- 2025Emotion estimation from video footage with LSTM23 Jan 2025
- 2024GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution21 Oct 2024
- 2024Using Prompts to Guide Large Language Models in Imitating a Real Person's Language Style4 Oct 2024
- 2024Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkit26 Sep 2024
- 2024Ig3D: Integrating 3D Face Representations in Facial Expression Inference29 Aug 2024
- 2024Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency4 Aug 2024
- 2024Affective Behaviour Analysis via Progressive Learning24 Jul 2024
- 2024Robust Facial Reactions Generation: An Emotion-Aware Framework with Modality Compensation22 Jul 2024
- 2024SAM2CLIP2SAM: Vision Language Model for Segmentation of 3D CT Scans for Covid-19 Detection22 Jul 2024
- 2024HSEmotion Team at the 7th ABAW Challenge: Multi-Task Learning and Compound Facial Expression Recognition18 Jul 2024
- 2024Temporal Label Hierachical Network for Compound Emotion Recognition17 Jul 2024
- 2024Textualized and Feature-based Models for Compound Multimodal Emotion Recognition in the Wild17 Jul 2024
50 newest of 110 All 110 (JSON)
- 2024The 6th Affective Behavior Analysis in-the-wild (ABAW) Competitioncited by 78
- 2024Distribution Matching for Multi-Task Learning of Classification Tasks: a Large-Scale Study on Faces & Beyondcited by 60
- 20247th ABAW Competition: Multi-Task Learning and Compound Expression Recognitioncited by 53
- 2023From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videoscited by 39
- 2024Domain adaptation, Explainability & Fairness in AI for Medical Image Analysis: Diagnosis of COVID-19 based on 3-D Chest CT-scanscited by 30
- 2023Multi-modal Facial Affective Analysis based on Masked Autoencodercited by 23
- 2024COVID-19 Computer-aided Diagnosis through AI-assisted CT Imaging Analysis: Deploying a Medical AI Systemcited by 23
- 2023Leveraging TCN and Transformer for effective visual-audio fusion in continuous emotion recognitioncited by 20
- 2023BTDNet: a Multi-Modal Approach for Brain Tumor Radiogenomic Classificationcited by 20
- 2024Affective Behaviour Analysis via Integrating Multi-Modal Knowledgecited by 18
- 2024Robust Light-Weight Facial Affective Behavior Recognition with CLIPcited by 16
- 2024Behaviour4All: in-the-wild Facial Behaviour Analysis Toolkitcited by 16
12 most cited of 106 All 106 (JSON)
- 2026AffectFuse: Cross-Task Feature Fusion with Temporal Modeling for Multi-Task Affective Behavior Analysis17 Jul 2026
- 2026HSEmotion Team at the 11th ABAW Challenge: Multi-Task Learning and Ambivalence/Hesitancy Video Recognition14 Jul 2026
- 2026Causal Supervision of Attention for Affective Behaviour Analysis13 Jul 2026
- 2026Strength-Parity Ensembling with Parameter-Isolated Experts for Multi-Task Affect Recognition12 Jul 2026
- 2026A Shared Latent for Partially-Labeled Multi-Task Facial Affect Recognition11 Jul 2026
- 2026The Circumplex Degeneracy Behind the Rare-Class Limit in Affect Recognition14 Jun 2026
- 2026SenBen: Sensitive Scene Graphs for Explainable Content Moderation9 Apr 2026
- 2026Anchoring Emotions in Text: Robust Multimodal Fusion for Mimicry Intensity Estimation16 Mar 2026
- 2026Team RAS in 10th ABAW Competition: Multimodal Valence and Arousal Estimation Approach13 Mar 2026
- 2026HSEmotion Team at ABAW-10 Competition: Facial Expression Recognition, Valence-Arousal Estimation, Action Unit Detection and Fine-Grained Violence Classification13 Mar 2026
- 2026A Two-Stage Dual-Modality Model for Facial Emotional Expression Recognition12 Mar 2026
- 2026Multimodal Emotion Recognition via Bi-directional Cross-Attention and Temporal Modeling12 Mar 2026
12 newest of 106 All 106 (JSON)